3  ETL

import os
from pandas.plotting import autocorrelation_plot
import warnings
import pandas as pd
import seaborn as sns
import requests
import plotly.express as px
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import plotly.graph_objects as go
from IPython.display import display
from scipy.stats import ks_2samp
# from TSPackages import *
from scipy.stats import jarque_bera
from scipy.stats import ks_2samp
from scipy.stats import kurtosis, skew
from statsmodels.graphics.tsaplots import plot_acf, plot_pacf
warnings.filterwarnings('ignore')
from pandas.plotting import autocorrelation_plot
import pandas as pd
import matplotlib.pyplot as plt
from statsmodels.tsa.seasonal import seasonal_decompose
import matplotlib.pyplot as plt
import os

file_path = [
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2019_A_31-12-2019.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2020_A_31-12-2020.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2021_A_31-12-2021.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2022_A_31-12-2022.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2023_A_31-12-2023.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2024_A_31-12-2024.CSV",
    r"C:\Users\Keyla Alba\OneDrive - Universidad del Norte\Doctorado (Ciencias)\Move La America\EDA\Datos\INMET_CO_MS_A710_PARANAIBA_01-01-2025_A_28-02-2025.CSV"
]

def load_and_clean(file_path):
    df = pd.read_csv(file_path, sep=';', encoding='latin1', skiprows=8)
    df.columns = [col.strip().upper() for col in df.columns]
    for col in df.columns:
        if "RADIACAO" in col and "KJ" in col:
            df.rename(columns={col: "RADIACAO_GLOBAL"}, inplace=True)
            break
    df['HORA UTC'] = df['HORA UTC'].astype(str).str.replace(' UTC', '', regex=False)
    df['HORA UTC'] = df['HORA UTC'].str.zfill(4)
    df['HORA UTC'] = df['HORA UTC'].str[:2] + ':' + df['HORA UTC'].str[2:4]
    df['datetime'] = pd.to_datetime(df['DATA'] + ' ' + df['HORA UTC'], format='%Y/%m/%d %H:%M', errors='coerce')
    df['RADIACAO_GLOBAL'] = pd.to_numeric(df['RADIACAO_GLOBAL'], errors='coerce').fillna(0)
    return df[['datetime', 'RADIACAO_GLOBAL']]
df_INMET = pd.concat([load_and_clean(fp) for fp in file_path], ignore_index=True)
print(df_INMET.shape)
df_INMET.head(n=14)

(54024, 2)

	datetime	RADIACAO_GLOBAL
0	2019-01-01 00:00:00	0.0
1	2019-01-01 01:00:00	0.0
2	2019-01-01 02:00:00	0.0
3	2019-01-01 03:00:00	0.0
4	2019-01-01 04:00:00	0.0
5	2019-01-01 05:00:00	0.0
6	2019-01-01 06:00:00	0.0
7	2019-01-01 07:00:00	0.0
8	2019-01-01 08:00:00	0.0
9	2019-01-01 09:00:00	0.0
10	2019-01-01 10:00:00	0.0
11	2019-01-01 11:00:00	0.0
12	2019-01-01 12:00:00	0.0
13	2019-01-01 13:00:00	2434.0

fig_INMET = px.line(
    df_INMET,
    x='datetime',
    y='RADIACAO_GLOBAL',
    title='Radiación Global (KJ/m²) por Hora INMET (2019 a Febrero 2025)',
    labels={
        'datetime': 'Fecha y Hora',
        'RADIACAO_GLOBAL': 'Radiación (KJ/m²)'
    }
)
fig_INMET.update_layout(template='plotly_white', width=1100, height=500)
fig_INMET.show()

3.0.0.1 Imputación usando promedio estacional

Uno de los retos fundamentales en el análisis de series temporales de radiación solar es la presencia de valores faltantes, especialmente en estaciones meteorológicas con limitaciones técnicas o períodos de inestabilidad climática. Una alternativa eficaz para abordar este problema es la Regla de Imputación Estacional, la cual consiste en reemplazar los datos perdidos utilizando el promedio de los valores registrados en la misma hora y día de otros años o meses, respetando así la estacionalidad y patrones cíclicos propios de la variable. Esta técnica resulta particularmente adecuada para variables como la radiación solar, que presenta una fuerte dependencia temporal y comportamiento periódico. En este contexto, analizaron el rendimiento de métodos univariantes de imputación bajo diferentes condiciones climáticas, concluyendo que las estrategias basadas en estacionalidad ofrecen ventajas significativas en climas tropicales. De manera complementaria, enfatizan que una adecuada imputación mejora sustancialmente la precisión de modelos de predicción basados en aprendizaje automático, al reducir la incertidumbre asociada al preprocesamiento de datos meteorológicos.

Regla de Imputación Estacional

Supongamos que tienes una serie de datos:

• \(R_i\): valor de radiación en la observación \(i\)
• \(d_i\): día del año de la observación \(i\) (de 1 a 366)
• \(h_i\): hora del día de la observación \(i\) (de 0 a 23)

Para cada observación con valor faltante \(R_i = 0\), la imputación es:

\[ \hat{R}_i = \frac{1}{n_{d_i,h_i}} \sum_{j \in G(d_i,h_i)} R_j \]

Donde:

• \(\hat{R}_i\) es el valor imputado para la observación \(i\)
• \(G(d_i, h_i)\) es el conjunto de observaciones \(j\) donde \(R_j > 0\), y el día y la hora coinciden con \(d_i, h_i\)
• \(n_{d_i,h_i}\) es el número de valores disponibles en ese grupo

Si no existen datos en ese grupo:

\[ \hat{R}_i = 0 \]

df_INMET['RADIACAO_GLOBAL_IMPUTADA'] = df_INMET['RADIACAO_GLOBAL'].replace(0, pd.NA)
df_INMET['datetime'] = pd.to_datetime(df_INMET['datetime'])
df_INMET['dayofyear'] = df_INMET['datetime'].dt.dayofyear
df_INMET['hour'] = df_INMET['datetime'].dt.hour

tabla_promedios = df_INMET.groupby(['dayofyear', 'hour'])['RADIACAO_GLOBAL_IMPUTADA'].mean()
def imputar_estacional(row):
    if pd.isna(row['RADIACAO_GLOBAL_IMPUTADA']):
        return tabla_promedios.get((int(row['dayofyear']), int(row['hour'])), 0)
    else:
        return row['RADIACAO_GLOBAL_IMPUTADA']
df_INMET['RADIACAO_GLOBAL_IMPUTADA'] = df_INMET.apply(imputar_estacional, axis=1)
df_INMET['RADIACAO_GLOBAL_IMPUTADA'] = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].fillna(0)
print(df_INMET.shape)
df_INMET.tail(20)

(54024, 5)

	datetime	RADIACAO_GLOBAL	RADIACAO_GLOBAL_IMPUTADA	dayofyear	hour
54004	2025-02-28 04:00:00	0.0	0.0	59	4
54005	2025-02-28 05:00:00	0.0	0.0	59	5
54006	2025-02-28 06:00:00	0.0	0.0	59	6
54007	2025-02-28 07:00:00	0.0	0.0	59	7
54008	2025-02-28 08:00:00	0.0	0.0	59	8
54009	2025-02-28 09:00:00	0.0	0.0	59	9
54010	2025-02-28 10:00:00	0.0	0.0	59	10
54011	2025-02-28 11:00:00	0.0	0.0	59	11
54012	2025-02-28 12:00:00	0.0	1749.0	59	12
54013	2025-02-28 13:00:00	0.0	0.0	59	13
54014	2025-02-28 14:00:00	0.0	2989.0	59	14
54015	2025-02-28 15:00:00	0.0	0.0	59	15
54016	2025-02-28 16:00:00	0.0	1930.0	59	16
54017	2025-02-28 17:00:00	0.0	0.0	59	17
54018	2025-02-28 18:00:00	0.0	3146.0	59	18
54019	2025-02-28 19:00:00	0.0	0.0	59	19
54020	2025-02-28 20:00:00	0.0	0.0	59	20
54021	2025-02-28 21:00:00	0.0	0.0	59	21
54022	2025-02-28 22:00:00	0.0	97.0	59	22
54023	2025-02-28 23:00:00	0.0	0.0	59	23

fig = go.Figure()
fig.add_trace(go.Scatter(
    x=df_INMET['datetime'],
    y=df_INMET['RADIACAO_GLOBAL_IMPUTADA'],
    mode='lines',
    name='INMET-IMPUTADA',
    line=dict(color='orange'),
    opacity=0.7
))
fig.add_trace(go.Scatter(
    x=df_INMET['datetime'],
    y=df_INMET['RADIACAO_GLOBAL'],
    mode='lines',
    name='INMET-SIN IMPUTAR',
    line=dict(color='blue'),
    opacity=0.7
))
fig.update_layout(
    title='Evolución de Radiación INMET - Imputación Promedio Estacional (2019-2025)',
    xaxis_title='Fecha y Hora',
    yaxis_title='Radiación (KJ/m²)',
    legend_title='Fuente',
    template='plotly_white',
    height=500,
    width=1100
)
fig.show()

rad_orig = df_INMET['RADIACAO_GLOBAL'][df_INMET['RADIACAO_GLOBAL'] > 0]
rad_imp = df_INMET['RADIACAO_GLOBAL_IMPUTADA'][df_INMET['RADIACAO_GLOBAL_IMPUTADA'] > 0]

fig, axes = plt.subplots(1, 2, figsize=(16, 5), sharey=True)

sns.histplot(rad_orig, bins=60, kde=True, color='royalblue', ax=axes[0])
axes[0].set_title('RADIACAO_GLOBAL (> 0)')
axes[0].set_xlabel('Radiación (KJ/m²)')
axes[0].set_ylabel('Frecuencia')
axes[0].grid(True)

sns.histplot(rad_imp, bins=60, kde=True, color='darkorange', ax=axes[1])
axes[1].set_title('RADIACAO_GLOBAL_IMPUTADA (> 0)')
axes[1].set_xlabel('Radiación (KJ/m²)')
axes[1].set_ylabel('')
axes[1].grid(True)

fig.suptitle('Distribuciones de Radiación Solar INMET (Imputación Promedio Estacional) (> 0) - Antes y Después ', fontsize=16)
plt.tight_layout()
plt.show()

rad_orig = df_INMET['RADIACAO_GLOBAL'][df_INMET['RADIACAO_GLOBAL'] > 0]
rad_imp = df_INMET['RADIACAO_GLOBAL_IMPUTADA'][df_INMET['RADIACAO_GLOBAL_IMPUTADA'] > 0]
stat_ks, p_ks = ks_2samp(rad_orig, rad_imp)
print("Kolmogorov-Smirnov Test (Distribución Original vs Imputada):")
print(f"Estadístico KS: {stat_ks:.4f}")
print(f"p-valor: {p_ks:.4e}")
if p_ks > 0.05:
    print("No se rechaza H0 → Las distribuciones son estadísticamente similares.")
else:
    print("Se rechaza H0 → Las distribuciones son diferentes.")

Kolmogorov-Smirnov Test (Distribución Original vs Imputada):
Estadístico KS: 0.0153
p-valor: 8.3915e-01
No se rechaza H0 → Las distribuciones son estadísticamente similares.

3.0.0.2 EDA

En el contexto de la predicción de radiación solar mediante modelos de series de tiempo, es fundamental conservar la estructura completa de la serie, incluyendo los valores de radiación nocturna igual a cero. El mantenimiento de esta continuidad temporal asegura que los algoritmos puedan captar correctamente la dinámica estacional y los ciclos diarios, evitando la introducción de sesgos por omisión de periodos sin registros. Este enfoque es especialmente relevante al trabajar con modelos como redes neuronales recurrentes, regresión de soporte vectorial o procesos gaussianos, los cuales requieren secuencias homogéneas y completas para una convergencia adecuada y generalización efectiva .

Adicionalmente, investigaciones que comparan arquitecturas híbridas de redes neuronales han resaltado que la inclusión de todos los datos horarios incluyendo los correspondientes a la noche contribuye a un entrenamiento más robusto y coherente, permitiendo una mejor adaptación a diferentes contextos geográficos y meteorológicos .

3.0.0.2.1 Horas

df_INMET.to_csv('df_INMET.csv', index=False)

df_INMET['datetime'] = pd.to_datetime(df_INMET['datetime'])
fig = px.line(df_INMET, 
              x='datetime', 
              y='RADIACAO_GLOBAL_IMPUTADA',
              title='Time Series - Global Radiation',
              labels={'datetime': 'Date', 'RADIACAO_GLOBAL_IMPUTADA': 'Radiation'})

fig.update_layout(
    xaxis_title='Fecha',
    yaxis_title='Radiación',
    template='plotly_white',
    width=1000,
    height=500
)
fig.show()

df_INMET['datetime'] = pd.to_datetime(df_INMET['datetime'])
df_INMET = df_INMET.set_index('datetime')
os.makedirs("figures", exist_ok=True)
plt.figure(figsize=(14, 5))
plt.plot(df_INMET['RADIACAO_GLOBAL_IMPUTADA'], color='blue')
plt.title('Time Series - Global Radiation', fontsize=18)
plt.xlabel('Date', fontsize=14)
plt.ylabel('Radiation (W/m²)', fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/Global_Radiation_TimeSeries.png", dpi=300)
plt.show()

import pandas as pd
import matplotlib.pyplot as plt
import os

año_inicio = 2019
fechas_completas = pd.date_range(start=f"{año_inicio}-01-01 00:00:00", periods=len(df_INMET), freq='H')
df_INMET['datetime'] = fechas_completas
df_INMET = df_INMET.set_index('datetime')
fig, ax = plt.subplots(figsize=(14, 5))
ax.plot(df_INMET.index, df_INMET['RADIACAO_GLOBAL_IMPUTADA'], color='blue')
ax.set_title('Time Series - Global Radiation', fontsize=18)
ax.set_xlabel('Date', fontsize=14)
ax.set_ylabel('Radiation (W/m²)', fontsize=14)
ax.grid(True)
interval_start = pd.Timestamp("2020-01-10 00:00:00")
interval_end = pd.Timestamp("2020-01-15 00:00:00")
zoom_data = df_INMET.loc[interval_start:interval_end]
ax_inset = fig.add_axes([0.6, 0.45, 0.25, 0.4])  # [left, bottom, width, height]
ax_inset.plot(zoom_data.index, zoom_data['RADIACAO_GLOBAL_IMPUTADA'], color='red')
ax_inset.set_title('Zoom: Jan 10–15, 2020', fontsize=10)
ax_inset.grid(True)
ax_inset.set_xticks([])
ax_inset.set_yticks([])
ax_inset.set_xlabel('')
ax_inset.set_ylabel('')
os.makedirs("figures", exist_ok=True)
plt.tight_layout()
plt.savefig("figures/Global_Radiation_TimeSeries_Zoom.png", dpi=300)
plt.show()

variables = ['RADIACAO_GLOBAL_IMPUTADA']
resumen = {}
for var in variables:
    data = df_INMET[var]  
    resumen[var] = {
        'N_records': len(data),
        'μ': data.mean(),
        'σ': data.std(),
        'y_min': data.min(),
        'Q1': data.quantile(0.25),
        'x̄': data.median(),
        'Q3': data.quantile(0.75),
        'y_max': data.max(),
        'Kurtosis': data.kurtosis(),
        'Skewness': data.skew()
    }
df_resumen = pd.DataFrame(resumen)
df_resumen

	RADIACAO_GLOBAL_IMPUTADA
N_records	54024.000000
μ	284.327790
σ	752.818778
y_min	0.000000
Q1	0.000000
x̄	0.000000
Q3	0.000000
y_max	3924.000000
Kurtosis	6.500850
Skewness	2.742065

from statsmodels.tsa.seasonal import seasonal_decompose
descomposicion = seasonal_decompose(df_INMET['RADIACAO_GLOBAL_IMPUTADA'].tail(1000), model='additive', period=24)
descomposicion.plot()
plt.suptitle("Decomposition of Global Radiation (Daily Cycle)", fontsize=16)
plt.tight_layout()
plt.show()

desc_por_hora = df_INMET.groupby('hour')['RADIACAO_GLOBAL_IMPUTADA'].describe()
desc_por_hora

	count	mean	std	min	25%	50%	75%	max
hour
0	2251.0	0.021324	0.291339	0.0	0.0	0.0	0.0	4.0
1	2251.0	0.024434	0.287252	0.0	0.0	0.0	0.0	5.0
2	2251.0	0.009329	0.167072	0.0	0.0	0.0	0.0	3.0
3	2251.0	0.032430	0.292600	0.0	0.0	0.0	0.0	4.0
4	2251.0	0.015549	0.184338	0.0	0.0	0.0	0.0	3.0
5	2251.0	0.011550	0.132832	0.0	0.0	0.0	0.0	2.0
6	2251.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0
7	2251.0	0.005775	0.075792	0.0	0.0	0.0	0.0	1.0
8	2251.0	0.000000	0.000000	0.0	0.0	0.0	0.0	0.0
9	2251.0	0.822301	4.227157	0.0	0.0	0.0	0.0	51.0
10	2251.0	32.930920	96.786907	0.0	0.0	0.0	0.0	666.0
11	2251.0	185.690582	346.654214	0.0	0.0	0.0	262.0	1656.0
12	2251.0	443.797201	687.757224	0.0	0.0	0.0	913.0	2524.0
13	2251.0	593.693470	917.315057	0.0	0.0	0.0	1498.0	3033.0
14	2251.0	901.893159	1242.582789	0.0	0.0	0.0	2175.0	3425.0
15	2251.0	935.042870	1337.877727	0.0	0.0	0.0	2449.0	3793.0
16	2251.0	1129.770546	1418.127255	0.0	0.0	0.0	2611.0	3924.0
17	2251.0	834.166148	1219.894113	0.0	0.0	0.0	2212.0	3782.0
18	2251.0	775.424256	1051.873855	0.0	0.0	0.0	1827.0	3568.0
19	2251.0	499.856952	767.244822	0.0	0.0	0.0	1114.0	2760.0
20	2251.0	344.708796	527.554926	0.0	0.0	0.0	737.0	1999.0
21	2251.0	127.717015	245.809561	0.0	0.0	0.0	185.0	1276.0
22	2251.0	18.125722	60.460133	0.0	0.0	0.0	1.0	639.0
23	2251.0	0.106619	0.705033	0.0	0.0	0.0	0.0	9.0

descomposicion = seasonal_decompose(df_INMET['RADIACAO_GLOBAL_IMPUTADA'].tail(1000), model='additive', period=24)
fig = descomposicion.plot()
fig.suptitle("Decomposition of Global Radiation (Daily Cycle)", fontsize=16)
plt.tight_layout()
fig.savefig('figures/decomposition_global_radiation.png')
plt.show()

os.makedirs('figures', exist_ok=True)
media_por_hora = df_INMET.groupby('hour')['RADIACAO_GLOBAL_IMPUTADA'].mean().reset_index()
plt.figure(figsize=(8, 6))
sns.lineplot(data=media_por_hora, x='hour', y='RADIACAO_GLOBAL_IMPUTADA', marker='o')
plt.title('Average Global Radiation by Hour', fontsize=16)
plt.xlabel('Hour of Day', fontsize=12)
plt.ylabel('Global Radiation', fontsize=12)
plt.xticks(range(0, 24))
plt.grid(True)
plt.savefig('figures/avg_radiation_by_hour.png')
plt.show()

os.makedirs('figures', exist_ok=True)

if 'hour' not in df_INMET.columns:
    df_INMET['hour'] = df_INMET.index.hour
fig = px.box(
    df_INMET,
    x='hour',
    y='RADIACAO_GLOBAL_IMPUTADA',
    labels={
        'hour': 'Hour of Day',
        'RADIACAO_GLOBAL_IMPUTADA': 'Global Radiation'
    },
    title='Distribution of Global Radiation by Hour of the Day'
)

fig.update_layout(
    title_font_size=18,
    xaxis_title_font_size=14,
    yaxis_title_font_size=14
)
fig.write_html("figures/boxplot_radiation_by_hour_plotly.html")
fig.show()

os.makedirs('figures', exist_ok=True)
if 'hour' not in df_INMET.columns:
    df_INMET['hour'] = df_INMET.index.hour
plt.figure(figsize=(10, 6))
sns.boxplot(data=df_INMET, x='hour', y='RADIACAO_GLOBAL_IMPUTADA')
plt.title('Distribution of Global Radiation by Hour of the Day', fontsize=18)
plt.xlabel('Hour of Day', fontsize=14)
plt.ylabel('Global Radiation', fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig('figures/boxplot_radiation_by_hour.png', dpi=300)
plt.show()

os.makedirs('figures', exist_ok=True)
plt.figure(figsize=(5, 4))
autocorrelation_plot(df_INMET['RADIACAO_GLOBAL_IMPUTADA'].tail(200))
plt.title("Autocorrelation - Global Radiation", fontsize=14)
plt.grid(True)
plt.savefig("figures/autocorrelation_global_radiation.png")
plt.show()

from statsmodels.graphics.tsaplots import plot_pacf

os.makedirs("figures", exist_ok=True)
plt.figure(figsize=(5, 4))
plot_pacf(df_INMET['RADIACAO_GLOBAL_IMPUTADA'].tail(2000), lags=100, method='ywm')
plt.title("PACF - Global Radiation (Hourly Series)", fontsize=12)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/pacf_hourly_compact.png")
plt.show()

<Figure size 500x400 with 0 Axes>

3.0.0.3 EDA DIARIA

df_diario = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('D').mean()
variables = ['RADIACAO_GLOBAL_IMPUTADA']
resumen = {}

for var in variables:
    data = df_diario  
    resumen[var] = {
        'N_records': len(data),
        'μ': data.mean(),
        'σ': data.std(),
        'y_min': data.min(),
        'Q1': data.quantile(0.25),
        'x̄': data.median(),
        'Q3': data.quantile(0.75),
        'y_max': data.max(),
        'Kurtosis': data.kurtosis(),
        'Skewness': data.skew()
    }
df_resumen = pd.DataFrame(resumen)
df_resumen

	RADIACAO_GLOBAL_IMPUTADA
N_records	2251.000000
μ	284.327790
σ	142.219504
y_min	0.000000
Q1	187.916667
x̄	263.104167
Q3	369.541667
y_max	799.916667
Kurtosis	0.287621
Skewness	0.546791

os.makedirs("figures", exist_ok=True)
interval_start = "2022-01-01"
interval_end = "2022-03-01"
fig, ax = plt.subplots(figsize=(14, 5))
ax.plot(df_diario, color='blue')
ax.set_title('Daily Time Series - Global Radiation', fontsize=18)
ax.set_xlabel('Date', fontsize=12)
ax.set_ylabel('Global Radiation', fontsize=12)
ax.grid(True)
ax.axvspan(pd.to_datetime(interval_start), pd.to_datetime(interval_end),
           color='gray', alpha=0.3, label='Zoom region')
ax_inset = fig.add_axes([0.55, 0.50, 0.3, 0.35])  # [x, y, width, height]
zoom_data = df_diario.loc[interval_start:interval_end]
ax_inset.plot(zoom_data, color='red')
ax_inset.set_title('Zoom: Jan–Mar 2022', fontsize=10)
ax_inset.set_xticks([])
ax_inset.set_yticks([])
plt.tight_layout()
plt.savefig("figures/daily_series_with_zoom_highlighted.png")
plt.show()

descomposicion = seasonal_decompose(df_diario.tail(200), model='additive', period=7)
descomposicion.plot()
plt.suptitle('Descomposición de Radiación Global (ciclo semanal - 7 días)', fontsize=16)
plt.tight_layout()
plt.show()

df_INMET['day_of_week'] = df_INMET.index.day_name()
desc_por_dia = df_INMET.groupby('day_of_week')['RADIACAO_GLOBAL_IMPUTADA'].describe()
orden_dias = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
desc_por_dia = desc_por_dia.loc[orden_dias]
desc_por_dia
desc_por_dia = df_INMET.groupby('day_of_week')['RADIACAO_GLOBAL_IMPUTADA'].describe()
orden_dias = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
desc_por_dia = desc_por_dia.loc[orden_dias]
desc_por_dia

	count	mean	std	min	25%	50%	75%	max
day_of_week
Monday	7704.0	276.915390	740.072654	0.0	0.0	0.0	0.0	3924.0
Tuesday	7728.0	288.041990	760.135891	0.0	0.0	0.0	0.0	3924.0
Wednesday	7728.0	281.359645	747.620231	0.0	0.0	0.0	0.0	3924.0
Thursday	7728.0	284.264644	751.770750	0.0	0.0	0.0	0.0	3869.0
Friday	7728.0	285.984170	756.346878	0.0	0.0	0.0	0.0	3924.0
Saturday	7704.0	285.550299	753.603337	0.0	0.0	0.0	0.0	3924.0
Sunday	7704.0	288.171102	760.189282	0.0	0.0	0.0	0.0	3924.0

os.makedirs("figures", exist_ok=True)
average_by_day = df_INMET.groupby(df_INMET.index.day_name())['RADIACAO_GLOBAL_IMPUTADA'].mean().reindex(
    ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
).reset_index()
average_by_day.columns = ['Day', 'Average Radiation']
plt.figure(figsize=(8, 6))
sns.lineplot(data=average_by_day, x='Day', y='Average Radiation', marker='o')
plt.title('Average Global Radiation by Day of the Week', fontsize=18)
plt.xlabel('Day of the Week', fontsize=14)
plt.ylabel('Global Radiation', fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/Average_Radiation_by_Day.png", dpi=300)
plt.show()

os.makedirs("figures", exist_ok=True)

daily_series = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('D').mean().dropna()
df_daily = daily_series.to_frame(name='RADIACAO_GLOBAL_IMPUTADA')
df_daily['Day'] = df_daily.index.day_name()
days_order = ['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
fig = px.box(
    df_daily,
    x='Day',
    y='RADIACAO_GLOBAL_IMPUTADA',
    category_orders={'Day': days_order},
    labels={
        'Day': 'Day of the Week',
        'RADIACAO_GLOBAL_IMPUTADA': 'Global Radiation (Imputed)'
    },
    title='Distribution of Imputed Global Radiation by Day of the Week'
)

fig.update_layout(
    title_font_size=18,
    xaxis_title_font_size=14,
    yaxis_title_font_size=14
)
fig.write_html("figures/Boxplot_GlobalRadiation_ByDay_Plotly.html")
fig.show()

os.makedirs("figures", exist_ok=True)
daily_series = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('D').mean().dropna()
df_daily = daily_series.to_frame(name='RADIACAO_GLOBAL_IMPUTADA')
df_daily['Day'] = df_daily.index.day_name()
plt.figure(figsize=(10, 6))
sns.boxplot(
    data=df_daily,
    x='Day',
    y='RADIACAO_GLOBAL_IMPUTADA',
    order=['Monday', 'Tuesday', 'Wednesday', 'Thursday', 'Friday', 'Saturday', 'Sunday']
)
plt.title('Distribution of Imputed Global Radiation by Day of the Week', fontsize=18)
plt.xlabel('Day of the Week', fontsize=14)
plt.ylabel('Global Radiation (Imputed)', fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/Boxplot_GlobalRadiation_ByDay.png", dpi=300)
plt.show()

plt.figure(figsize=(6, 4))
autocorrelation_plot(daily_series.tail(200))
plt.title("Autocorrelation - Global Radiation", fontsize=12)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/Autocorrelation_GlobalRadiation_Daily_200days.png", dpi=300)
plt.show()

plt.figure(figsize=(10, 4))
plot_pacf(daily_series.tail(2000), lags=150, method='ywm')  
plt.title("PACF - Global Radiation (Daily Series)", fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/PACF_GlobalRadiation_DailySeries.png", dpi=300)
plt.show()

<Figure size 1000x400 with 0 Axes>

3.0.0.3.1 EDA MENSUAL

df_mensual = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('M').mean().to_frame(name='Promedio_Radiacion_Mensual')
variables = ['Promedio_Radiacion_Mensual']
resumen = {}
for var in variables:
    data = df_mensual[var]
    resumen[var] = {
        'N_records': len(data),
        'μ': data.mean(),
        'σ': data.std(),
        'y_min': data.min(),
        'Q1': data.quantile(0.25),
        'x̄': data.median(),
        'Q3': data.quantile(0.75),
        'y_max': data.max(),
        'Kurtosis': data.kurtosis(),
        'Skewness': data.skew()
    }
df_resumen = pd.DataFrame(resumen)
df_resumen

	Promedio_Radiacion_Mensual
N_records	74.000000
μ	284.331526
σ	49.663561
y_min	225.783565
Q1	249.974238
x̄	274.986044
Q3	313.849497
y_max	411.725806
Kurtosis	1.182565
Skewness	1.264723

plt.figure(figsize=(14, 5))
plt.plot(df_mensual, color='blue')
plt.title('Monthly Time Series - Global Radiation', fontsize=18)
plt.xlabel('Date', fontsize=18)
plt.ylabel('Radiation (W/m²)', fontsize=18)
plt.xticks(fontsize=16) 
plt.yticks(fontsize=16)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/Monthly_GlobalRadiation_TimeSeries.png", dpi=300)
plt.show()

descomposicion = seasonal_decompose(df_mensual, model='additive', period=12)
descomposicion.plot()
plt.suptitle('Decomposition of Global Radiation (Monthly Cycle)', fontsize=16)
plt.tight_layout()
plt.show()

df_diario = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('D').mean()
df_diario = df_diario.to_frame(name='RADIACAO_GLOBAL_IMPUTADA')
df_diario['Mes'] = df_diario.index.month
agrupado_mes_calendario = df_diario.groupby('Mes')['RADIACAO_GLOBAL_IMPUTADA']
resumen_mensual_simple = pd.DataFrame({
    'N_records': agrupado_mes_calendario.count(),
    'μ': agrupado_mes_calendario.mean(),
    'σ': agrupado_mes_calendario.std(),
    'y_min': agrupado_mes_calendario.min(),
    'Q1': agrupado_mes_calendario.quantile(0.25),
    'x̄': agrupado_mes_calendario.median(),
    'Q3': agrupado_mes_calendario.quantile(0.75),
    'y_max': agrupado_mes_calendario.max(),
    'Kurtosis': agrupado_mes_calendario.apply(pd.Series.kurtosis),
    'Skewness': agrupado_mes_calendario.apply(pd.Series.skew)
})
resumen_mensual_simple.index = pd.to_datetime(resumen_mensual_simple.index, format='%m').month_name()
resumen_mensual_simple

	N_records	μ	σ	y_min	Q1	x̄	Q3	y_max	Kurtosis	Skewness
Mes
January	217	407.477151	163.626147	68.500000	283.104167	383.895833	516.208333	799.916667	-0.371655	0.164949
February	198	317.083649	133.032529	53.875000	235.833333	304.166667	392.291667	659.645833	0.033322	0.372261
March	186	234.346550	127.571404	3.875000	154.541667	225.500000	298.250000	610.666667	1.327689	0.917040
April	180	237.857407	141.355477	0.583333	140.453125	232.500000	306.776042	596.875000	0.105675	0.537886
May	186	257.869848	113.049078	69.791667	160.177083	244.722222	350.583333	518.916667	-0.768204	0.174336
June	180	230.266204	111.890502	0.000000	147.541667	226.770833	324.916667	430.125000	-0.636302	-0.359935
July	186	252.023746	137.279431	27.916667	168.791667	217.583333	357.541667	630.291667	0.256444	0.710706
August	186	277.110215	101.562718	61.750000	210.166667	274.187500	344.500000	494.375000	-0.488741	-0.054911
September	180	274.390278	129.997583	40.041667	181.416667	258.791667	339.291667	579.208333	-0.158738	0.444753
October	186	321.683580	149.988278	60.333333	185.083333	332.604167	430.125000	668.291667	-0.582618	0.048882
November	180	291.265625	137.199636	32.208333	196.562500	267.375000	364.041667	687.604167	0.801704	0.766444
December	186	284.581317	139.366372	28.833333	194.666667	253.104167	382.250000	743.041667	0.707201	0.739721

promedio_por_mes = df_INMET.groupby(df_INMET.index.month)['RADIACAO_GLOBAL_IMPUTADA'].mean()
promedio_por_mes.index = pd.to_datetime(promedio_por_mes.index, format='%m').month_name()
promedio_por_mes = promedio_por_mes.reset_index()
promedio_por_mes.columns = ['Month', 'Average Radiation']
orden_meses = ['January', 'February', 'March', 'April', 'May', 'June',
               'July', 'August', 'September', 'October', 'November', 'December']
promedio_por_mes = promedio_por_mes.set_index('Month').loc[orden_meses].reset_index()
plt.figure(figsize=(12, 6))
sns.lineplot(data=promedio_por_mes, x='Month', y='Average Radiation', marker='o')
plt.title('Average Global Radiation by Month of the Year', fontsize=18)
plt.xlabel('Month of the Year', fontsize=14)
plt.ylabel('Global Radiation (Imputed)', fontsize=14)
plt.xticks(fontsize=13) 
plt.yticks(fontsize=13)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/avg_radiation_by_month.png", dpi=300)
plt.show()

df_INMET['Month'] = df_INMET.index.month
df_INMET['Month'] = pd.to_datetime(df_INMET['Month'], format='%m').dt.month_name()
month_order = ['January', 'February', 'March', 'April', 'May', 'June',
               'July', 'August', 'September', 'October', 'November', 'December']

os.makedirs("figures", exist_ok=True)
plt.figure(figsize=(14, 6))
sns.violinplot(
    data=df_INMET,
    x='Month',
    y='RADIACAO_GLOBAL_IMPUTADA',
    order=month_order,
    inner='box'  
)
plt.title('Distribution of Global Radiation by Month', fontsize=18)
plt.xlabel('Month', fontsize=16)
plt.ylabel('Global Radiation', fontsize=16)
plt.xticks(fontsize=14) 
plt.yticks(fontsize=14)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/violinplot_radiation_by_month.png", dpi=300)
plt.show()

df_INMET['Month'] = pd.Categorical(df_INMET['Month'], categories=month_order, ordered=True)

fig = px.violin(
    df_INMET,
    x='Month',
    y='RADIACAO_GLOBAL_IMPUTADA',
    category_orders={'Month': month_order},
    box=True,
    points=False,  
    title='Distribution of Imputed Global Radiation by Month'
)

fig.update_layout(
    title_font_size=18,
    xaxis_title='Month',
    yaxis_title='Global Radiation (Imputed)',
    xaxis_tickangle=45,
    font=dict(size=12)
)
fig.show()

serie_mensual = df_INMET['RADIACAO_GLOBAL_IMPUTADA'].resample('M').mean()
plt.figure(figsize=(5, 4))
autocorrelation_plot(serie_mensual)
plt.title("Autocorrelation - Global Radiation (Monthly Series)", fontsize=12)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/autocorrelation_monthly_series.png", dpi=300)
plt.show()

plt.figure(figsize=(5, 4))
plot_pacf(serie_mensual, lags=30, method='ywm')
plt.title("PACF - Global Radiation (Monthly Series)", fontsize=12)
plt.grid(True)
plt.tight_layout()
plt.savefig("figures/pacf_monthly_series.png", dpi=300)
plt.show()

<Figure size 500x400 with 0 Axes>